Guardado en:
Detalles Bibliográficos
Autores principales: LaMaster, John, Das, Dhritiman, Kofler, Florian, Crane, Jason, Li, Yan, Lasser, Tobias, Menze, Bjoern H
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2409.06609
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909310830772224
author LaMaster, John
Das, Dhritiman
Kofler, Florian
Crane, Jason
Li, Yan
Lasser, Tobias
Menze, Bjoern H
author_facet LaMaster, John
Das, Dhritiman
Kofler, Florian
Crane, Jason
Li, Yan
Lasser, Tobias
Menze, Bjoern H
contents Magnetic resonance spectroscopic imaging is a widely available imaging modality that can non-invasively provide a metabolic profile of the tissue of interest, yet is challenging to integrate clinically. One major reason is the expensive, expert data processing and analysis that is required. Using machine learning to predict MRS-related quantities offers avenues around this problem, but deep learning models bring their own challenges, especially model trust. Current research trends focus primarily on mean error metrics, but comprehensive precision metrics are also needed, e.g. standard deviations, confidence intervals, etc.. This work highlights why more comprehensive error characterization is important and how to improve the precision of CNNs for spectral modeling, a quantitative task. The results highlight advantages and trade-offs of these techniques that should be considered when addressing such regression tasks with CNNs. Detailed insights into the underlying mechanisms of each technique, and how they interact with other techniques, are discussed in depth.
format Preprint
id arxiv_https___arxiv_org_abs_2409_06609
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving the Precision of CNNs for Magnetic Resonance Spectral Modeling
LaMaster, John
Das, Dhritiman
Kofler, Florian
Crane, Jason
Li, Yan
Lasser, Tobias
Menze, Bjoern H
Computer Vision and Pattern Recognition
Machine Learning
I.2.m; I.4.m
Magnetic resonance spectroscopic imaging is a widely available imaging modality that can non-invasively provide a metabolic profile of the tissue of interest, yet is challenging to integrate clinically. One major reason is the expensive, expert data processing and analysis that is required. Using machine learning to predict MRS-related quantities offers avenues around this problem, but deep learning models bring their own challenges, especially model trust. Current research trends focus primarily on mean error metrics, but comprehensive precision metrics are also needed, e.g. standard deviations, confidence intervals, etc.. This work highlights why more comprehensive error characterization is important and how to improve the precision of CNNs for spectral modeling, a quantitative task. The results highlight advantages and trade-offs of these techniques that should be considered when addressing such regression tasks with CNNs. Detailed insights into the underlying mechanisms of each technique, and how they interact with other techniques, are discussed in depth.
title Improving the Precision of CNNs for Magnetic Resonance Spectral Modeling
topic Computer Vision and Pattern Recognition
Machine Learning
I.2.m; I.4.m
url https://arxiv.org/abs/2409.06609